Instructions to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16

SGLang

How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16
```

ChibuUkachi commited on Jan 8

Commit

35e937f

verified ·

1 Parent(s): d2cc8b7

updated card errors

Browse files

Files changed (1) hide show

README.md +5 -36

README.md CHANGED Viewed

@@ -20,14 +20,8 @@ tags:
   - **Output:** Text
 - **Model Optimizations:**
   - **Weight quantization:** INT4
-- **Intended Use Cases:**
-  - Reasoning.
-  - Function calling.
-  - Subject matter experts via fine-tuning.
-  - Multilingual instruction following.
-  - Translation.
 - **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws).
-- **Release Date:** 05/05/2025
 - **Version:** 1.0
 - **Model Developers:** RedHat (Neural Magic)
@@ -71,7 +65,7 @@ generated_text = outputs[0].outputs[0].text
 print(generated_text)
 ```
-vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
 ## Creation
@@ -130,36 +124,18 @@ vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://do
 ## Evaluation
-The model was evaluated on the OpenLLM leaderboard tasks versions 2, using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness), and on reasoning tasks using [lighteval](https://github.com/neuralmagic/lighteval/tree/reasoning).
 [vLLM](https://docs.vllm.ai/en/stable/) was used for all evaluations.
 <details>
   <summary>Evaluation details</summary>
   **lm-evaluation-harness**
   ```
   lm_eval \
     --model vllm \
-    --model_args pretrained="RedHatAI/Qwen3-30B-A3B-Instruct-2507.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=15000,enable_chunk_prefill=True,tensor_parallel_size=1 \
-    --tasks openllm \
-    --apply_chat_template\
-    --fewshot_as_multiturn \
-    --batch_size auto
-  ```
-  ```
-  lm_eval \
-    --model vllm \
-    --model_args pretrained="RedHatAI/Qwen3-30B-A3B-Instruct-2507.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=15000,enable_chunk_prefill=True,tensor_parallel_size=1 \
-    --tasks mgsm \
-    --apply_chat_template\
-    --batch_size auto
-  ```
-  ```
-  lm_eval \
-    --model vllm \
-    --model_args pretrained="RedHatAI/Qwen3-30B-A3B-Instruct-2507.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=15000,enable_chunk_prefill=True,tensor_parallel_size=1 \
     --tasks leaderboard \
     --apply_chat_template\
     --fewshot_as_multiturn \
@@ -205,13 +181,6 @@ The model was evaluated on the OpenLLM leaderboard tasks versions 2, using [lm-e
     --use_chat_template = true
   ```
-  ```
-  lighteval vllm \
-    --model_args lighteval_model_arguments.yaml \
-    --tasks extended|lcb:codegeneration \
-    --use_chat_template = true
-  ```
 </details>
 ### Accuracy

   - **Output:** Text
 - **Model Optimizations:**
   - **Weight quantization:** INT4
 - **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws).
+- **Release Date:** 07/30/2025
 - **Version:** 1.0
 - **Model Developers:** RedHat (Neural Magic)
 print(generated_text)
 ```
+vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
 ## Creation
 ## Evaluation
+The model was evaluated on the OpenLLM leaderboard tasks versions 2, using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness), on reasoning tasks using [lighteval](https://github.com/neuralmagic/lighteval/tree/reasoning) and on LLM as a judge tasks using [ArenaHard](https://github.com/lmarena/arena-hard-auto).
 [vLLM](https://docs.vllm.ai/en/stable/) was used for all evaluations.
 <details>
   <summary>Evaluation details</summary>
   **lm-evaluation-harness**
   ```
   lm_eval \
     --model vllm \
+    --model_args pretrained="RedHatAI/Qwen3-30B-A3B-Instruct-2507.w4a16",dtype=auto,gpu_memory_utilization=0.9,max_model_len=40960,enable_chunk_prefill=True,tensor_parallel_size=1 \
     --tasks leaderboard \
     --apply_chat_template\
     --fewshot_as_multiturn \
     --use_chat_template = true
   ```
 </details>
 ### Accuracy